Tools #DeepSeek Nov 16, 2026 · Originally published Nov 13

DeepSeek opens its app's capabilities as APIs: web search, file input, URL reading and a safety check on deepseek-flash, with search at $0.75 per 1,000 calls

The search, file reading, link reading and safety layers behind the DeepSeek app are now switches in the API. Interface, compliance notes and prices, for teams building Q&A or document products who would rather not assemble the tool chain themselves.

Primary source DeepSeek API Docs changelog · api-docs.deepseek.com Read the original ↗

// Key points

  • deepseek-flash supports these in the Messages, Responses and Chat Completions APIs: the deepseek_web_search tool runs web or image searches and answers with citations, and with thinking enabled it searches and reads links on its own over several steps; PDFs, Office files and images are added to context after plain-text extraction or rich-layout parsing; deepseek_read_url fetches links found in the user's message.
  • A new safety check parameter reviews model input and output and returns a refusal marker when it finds a risk. DeepSeek says services offered to the public should enable it and meet obligations such as content safety review, large model registration and AI labeling.
  • The underlying capabilities are also standalone APIs: Search and Fetch, OCR, ASR and TTS. DeepSeek has open-sourced a demo chat client built on them that can import DeepSeek chat history.
  • Pricing: search and web fetch are $0.75 per 1,000 each, file parsing and OCR $0.225 per 1,000 pages; TTS lists at $0.45 per 10,000 characters and ASR at $0.116 per hour of audio, both currently 50% off.

Builder's takeFor AI Cloud Drive, file parsing at $0.225 per 1,000 pages is a cheap baseline. I would run my own scanned documents and tables through it and compare accuracy and cost per page with the current pipeline before replacing any part of it. Products serving users in China can turn the safety check on as a first line of defense, but it does not do the registration and labeling for you; your own review process still has to exist.

// Background · from #DeepSeek

Full timeline →
  1. Nov 13 DeepSeek V4-Pro, V4-Flash and V4.1-Flash arrive on SageMaker JumpStart: MIT-licensed MoE models with a 1M-token context
  2. Oct 18 DeepSeek releases V4.1-Flash-1017 under MIT: DeepSWE v1.1 rises from 74.2 to 77.0 and Terminal-Bench 4.0 from 31.2 to 42.3
  3. Oct 18 DeepSeek opens its Search and Fetch APIs to everyone at $0.75 per 1,000 calls per endpoint, free through Claude Code and Codex until October 31

Every Monday, the week in AI in one email

Every Monday morning: the 6 AI stories that mattered most in the past seven days, with my take, in your inbox.

Your email is only used to send the weekly and is never shared. Every email has a one-click unsubscribe link. See the latest issue →